INDEX
    Explanations

    references to religious commandments or prohibitions

    New Auto-Interp
    Negative Logits
    _puts
    -0.16
    atl
    -0.15
     Tobias
    -0.14
    ÑĢеÑħ
    -0.14
    igon
    -0.14
    orre
    -0.14
    ksam
    -0.13
    essian
    -0.13
    asin
    -0.13
    ussy
    -0.13
    POSITIVE LOGITS
     My
    0.17
    shall
    0.17
     shall
    0.17
     SHALL
    0.16
    ãģŁãģĹ
    0.16
    peÄį
    0.15
    ursed
    0.15
    Ñľ
    0.15
    agement
    0.14
     Separator
    0.14
    Act Density 0.076%

    No Known Activations